© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32687
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /manual
    -0.08
    amani
    -0.08
    poj
    -0.08
    ambu
    -0.07
     bowiem
    -0.07
    zman
    -0.07
    apati
    -0.07
    è«Ń
    -0.07
    aeda
    -0.07
    -cli
    -0.07
    POSITIVE LOGITS
     etc
    0.10
    çŃīçŃī
    0.10
    etc
    0.09
    以åıĬ
    0.07
    以åıĬåħ¶ä»ĸ
    0.07
    å¤ļå¤ļ
    0.06
     usw
    0.06
    以åıĬ对
    0.06
    ä¹ĥèĩ³
    0.06
    iele
    0.06
    Activations Density 0.848%

    No Known Activations